Learning parametric dynamic movement primitives from multiple demonstrations

Authors:
Takamitsu Matsubara;Sang-Ho Hyon;Jun Morimoto
Affiliations:
Nara Institute of Science and Technology, Japan and Department of Brain Robot Interface, ATR-CNS, Japan;Ritsumeikan University, Japan and Department of Brain Robot Interface, ATR-CNS, Japan;Department of Brain Robot Interface, ATR-CNS, Japan
Venue:
ICONIP'10 Proceedings of the 17th international conference on Neural information processing: theory and algorithms - Volume Part I
Year:
2010

Citing 6
Cited 0

Style machines

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Style translation for human motion

ACM SIGGRAPH 2005 Papers
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)

Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Multifactor Gaussian process models for style-content separation

Proceedings of the 24th international conference on Machine learning
Factored conditional restricted Boltzmann Machines for modeling motion style

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Learning and generalization of motor skills by learning from demonstration

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel approach to learn highly scalable Control Policies (CPs) of basis movement skills from multiple demonstrations. In contrast to conventional studies with a single demonstration, i.e., Dynamic Movement Primitives (DMPs) [1], our approach efficiently encodes multiple demonstrations by shaping a parametric-attractor landscape in a set of differential equations. This approach allows the learned CPs to synthesize novel movements with novel motion styles by specifying the linear coefficients of the bases as parameter vectors without losing useful properties of DMPs, such as stability and robustness against perturbations. For both discrete and rhythmic movement skills, we present a unified learning procedure for learning a parametric-attractor landscape from multiple demonstrations. The feasibility and highly extended scalability of DMPs are demonstrated on an actual dual-arm robot.